Problemsby IbisTrouble with Ollama never
MLOps2 posts from 2 people2d active+00 posts in the last 7 days, 0 the 7 days before (fading)Unverified
Posts per day
The posts behind it
2, newest firstOllama: native prompt_eval_cached_count is never mapped into prompt_tokens_details.cached_tokens (cache reads always report 0)### Describe the bug Ollama reports cached prompt tokens natively as `prompt_eval_cached_count` in its `/api/chat` response, and the OpenAI-compatible `/v1` endpoint reports it as `prompt_tokens_details.cached_tokens`. LiteLLM's ollama/ollama_chat handlers read only...BerriAI/litellm · nishfleet-worker[bot]Open ↗Windows 11 26200, Ollama 0.34.1 — tray app shows icon but never starts server; manual ollama serve works perfectly### What is the issue? Windows build 10.0.26200 Ollama 0.34.1, clean reinstall RTX 4070 + RTX 3060, CUDA v13, driver 13.1 Recent security updates: KB5129195 (15 Sep), KB5124007 + KB5126052 (09 Sep) Tray icon appears; curl http://127.0.0.1:11434/api/version fails; ollama list →...ollama/ollama · kavsak-gif3 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 2 places, about 1 a week over 21 days. Mostly on ollama/ollama, BerriAI/litellm. Tools named alongside: NVIDIA, OpenAI.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts about Ollama with no known issue, sharing the word "never". First post Sep 17, 2026, latest Oct 7, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
Other Ollama problems
Ollama upgrades break working setupsTrouble with Ollama pullRunning Ollama locally hits memory and speed limitsOllama error messages are crypticTrouble with Ollama chatTrouble with Ollama silentlyOllama users keep filing bugsTrouble with Ollama emptyServing models on Ollama is harder than it should beOllama runs out of context on real workTrouble with Ollama textOllama fails to return valid structured output
History
steady to fading
Trouble with Ollama never (2 posts)